skip to main content

Title: Data-Driven Decision-Theoretic Planning using Recurrent Sum-Product-Max Networks
Sum-product networks (SPN) are knowledge compilation models and are related to other graphical models for efficient probabilistic inference such as arithmetic circuits and AND/OR graphs. Recent investigations into generalizing SPNs have yielded sum-product-max networks (SPMN) which offer a data-driven alternative for decision making that has predominantly relied on handcrafted models. However, SPMNs are not suited for decision-theoretic planning which involves sequential decision making over multiple time steps. In this paper, we present recurrent SPMNs (RSPMN) that learn from and model decision-making data over time. RSPMNs utilize a template network that is unfolded as needed depending on the length of the data sequence. This is significant as RSPMNs not only inherit the benefits of SPNs in being data driven and mostly tractable, they are also well suited for planning problems. We establish soundness conditions on the template network, which guarantee that the resulting SPMN is valid, and present a structure learning algorithm to learn a sound template. RSPMNs learned on a testbed of data sets, some generated using RDDLSim, yield MEUs and policies that are close to the optimal on perfectly-observed domains and easily improve on a recent batch-constrained RL method, which is important because RSPMNs offer a new model-based approach to offline RL.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Proceedings of the International Conference on Automated Planning and Scheduling
Page Range / eLocation ID:
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The sum-product network (SPN) has been extended to model sequence data with the recurrent SPN (RSPN), and to decision-making problems with sum-product-max networks (SPMN). In this paper, we build on the concepts introduced by these extensions and present state-based recurrent SPMNs (S-RSPMNs) as a generalization of SPMNs to sequential decision-making problems where the state may not be perfectly observed. As with recurrent SPNs, S-RSPMNs utilize a repeatable template network to model sequences of arbitrary lengths. We present an algorithm for learning compact template structures by identifying unique belief states and the transitions between them through a state matching process that utilizes augmented data. In our knowledge, this is the first data-driven approach that learns graphical models for planning under partial observability, which can be solved efficiently. S-RSPMNs retain the linear solution complexity of SPMNs, and we demonstrate significant improvements in compactness of representation and the run time of structure learning and inference in sequential domains.

    more » « less
  2. In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide stateof-the-art performance in a wide variety of tasks, such as machine translation, headline generation, text summarization, speech-to-text conversion, and image caption generation. The underlying framework for all these models is usually a deep neural network comprising an encoder and a decoder. Although simple encoder–decoder models produce competitive results, many researchers have proposed additional improvements over these seq2seq models, e.g., using an attention-based model over the input, pointer-generation models, and self-attention models. However, such seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently, a completely novel point of view has emerged in addressing these two problems in seq2seq models, leveraging methods from reinforcement learning (RL). In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with seq2seq models that enable remembering long-term memories. We present some of the most recent frameworks that combine the concepts from RL and deep neural networks. Our work aims to provide insights into some of the problems that inherently arise with current approaches and how we can address them with better RL models. We also provide the source code for implementing most of the RL models discussed in this paper to support the complex task of abstractive text summarization and provide some targeted experiments for these RL models, both in terms of performance and training time. 
    more » « less
  3. Decision-making under uncertainty (DMU) is present in many important problems. An open challenge is DMU in non-stationary environments, where the dynamics of the environment can change over time. Reinforcement Learning (RL), a popular approach for DMU problems, learns a policy by interacting with a model of the environment offline. Unfortunately, if the environment changes the policy can become stale and take sub-optimal actions, and relearning the policy for the updated environment takes time and computational effort. An alternative is online planning approaches such as Monte Carlo Tree Search (MCTS), which perform their computation at decision time. Given the current environment, MCTS plans using high-fidelity models to determine promising action trajectories. These models can be updated as soon as environmental changes are detected to immediately incorporate them into decision making. However, MCTS’s convergence can be slow for domains with large state-action spaces. In this paper, we present a novel hybrid decision-making approach that combines the strengths of RL and planning while mitigating their weaknesses. Our approach, called Policy Augmented MCTS (PA-MCTS), integrates a policy’s actin-value estimates into MCTS, using the estimates to seed the action trajectories favored by the search. We hypothesize that PA-MCTS will converge more quickly than standard MCTS while making better decisions than the policy can make on its own when faced with nonstationary environments. We test our hypothesis by comparing PA-MCTS with pure MCTS and an RL agent applied to the classical CartPole environment. We find that PC-MCTS can achieve higher cumulative rewards than the policy in isolation under several environmental shifts while converging in significantly fewer iterations than pure MCTS. 
    more » « less
  4. Mobile wireless networks present several challenges for any learning system, due to uncertain and variable device movement, a decentralized network architecture, and constraints on network resources. In this work, we use deep reinforcement learning (DRL) to learn a scalable and generalizable forwarding strategy for such networks. We make the following contributions: i) we use hierarchical RL to design DRL packet agents rather than device agents, to capture the packet forwarding decisions that are made over time and improve training efficiency; ii) we use relational features to ensure generalizability of the learned forwarding strategy to a wide range of network dynamics and enable offline training; and iii) we incorporate both forwarding goals and network resource considerations into packet decision-making by designing a weighted DRL reward function. Our results show that our DRL agent often achieves a similar delay per packet delivered as the optimal forwarding strategy and outperforms all other strategies including state-of-the-art strategies, even on scenarios on which the DRL agent was not trained. 
    more » « less
  5. null (Ed.)
    Deep reinforcement learning (RL) has recently been successfully applied to networking contexts including routing, flow scheduling, congestion control, packet classification, cloud resource management, and video streaming. Deep-RL-driven systems automate decision making, and have been shown to outperform state-of-the-art handcrafted systems in important domains. However, the (typical) non-explainability of decisions induced by the deep learning machinery employed by these systems renders reasoning about crucial system properties, including correctness and security, extremely difficult. We show that despite the obscurity of decision making in these contexts, verifying that deep-RL-driven systems adhere to desired, designer-specified behavior, is achievable. To this end, we initiate the study of formal verification of deep RL and present Verily, a system for verifying deep-RL-based systems that leverages recent advances in verification of deep neural networks. We employ Verily to verify recently-introduced deep-RL-driven systems for adaptive video streaming, cloud resource management, and Internet congestion control. Our results expose scenarios in which deep-RL-driven decision making yields undesirable behavior. We discuss guidelines for building deep-RL-driven systems that are both safer and easier to verify. 
    more » « less